AI Agents & Automation

Zefort is a European CLM (Contract Lifecycle Management) platform designed for regulated organizations, offering continuous contract control. It helps structure complex contracts into measurable data, enabling better management of obligations, compliance, and financial risk. Key features include a centralized contract repository, automated obligation tracking, and AI-powered insights for large contract archives. Zefort also provides tools for creating consistent contract templates, collecting legally binding e-signatures with Zefort Sign, and integrating with existing systems. The platform emphasizes high security and compliance standards, including ISO 27001 certification and AES-256 encryption, with all data hosted within the EU.

FlaiChat is a superpowered chat application designed to bridge language barriers for multilingual families and groups. It offers automatic and instant translations for messages across more than 40 languages, ensuring seamless communication without the need for manual translation or language pack downloads. A standout feature is its voice translation capability, where users can create a voice clone and have their messages spoken in another language using their own voice. FlaiChat is free to download and use, available on iOS and Android, with desktop and web versions in development. It also supports hybrid languages like Hinglish and Spanglish, making it versatile for diverse communication needs.

Applied Intuition is a leading provider of physical AI solutions, specializing in automating machines across diverse industries including automotive, defense, trucking, mining, construction, and agriculture. The platform offers a comprehensive toolchain for the development, testing, and deployment of autonomous systems. Key offerings include a Vehicle OS, advanced autonomy stacks, and simulation tools that enable rapid development and validation of ADAS and AD software. Applied Intuition's solutions leverage AI and machine learning to enhance vehicle performance, optimize energy efficiency, and enable advanced features like predictive maintenance and autonomous driving capabilities. The modular architecture allows for seamless integration with existing vehicle systems, supporting a pathway from L2++ to L3 and L4 autonomy.

Sapio AI is an innovative AI-powered coaching tool designed to help individuals master critical communication skills such as emotional intelligence, active listening, storytelling, leadership, and conflict resolution. Users engage in lifelike AI conversations and receive instant, private feedback on every message, fostering a judgment-free environment for skill development. The platform offers over 25 scenarios and supports 10 languages, making it accessible to a wide range of learners. Sapio's feedback loop analyzes tone and phrasing, providing actionable insights and real-time tips to deepen connections and build trust. It also includes intuitive analytics to track transformation, ensuring users can monitor their progress in becoming more effective and confident communicators. All practice sessions are completely confidential, prioritizing user privacy and creating a safe space for growth.

LLMLingua is a powerful tool designed to optimize the performance of Large Language Models (LLMs) by significantly compressing prompts and KV-caches. This innovative approach, detailed in research papers presented at EMNLP'23 and ACL'24, allows for up to 20x compression while maintaining minimal performance degradation. The tool helps overcome common LLM challenges such as token limits, high API costs, and the 'lost in the middle' issue for long contexts. LLMLingua offers various versions, including LongLLMLingua for enhanced long-context processing and LLMLingua-2 for faster, task-agnostic compression. It also features SecurityLingua, a safety guardrail model for detecting and mitigating jailbreak attacks through security-aware prompt compression. The tool is integrated into popular frameworks like LangChain and LlamaIndex, making it accessible for developers working on LLM-based applications.

Mini-Omni is an open-source multimodal large language model designed for real-time, end-to-end speech input and streaming audio output conversational capabilities. It allows the model to "talk while thinking," generating text and audio simultaneously without requiring separate ASR or TTS models. The project provides features like real-time speech-to-speech conversations, streaming audio output, and batch inference options for "Audio-to-Text" and "Audio-to-Audio" tasks. Built on Qwen2 as the LLM backbone, litGPT for training and inference, Whisper for audio encoding, and snac for audio decoding, Mini-Omni is ideal for developers and researchers looking to experiment with and build upon advanced conversational AI models.

Gather AI offers a Physical AI solution for intralogistics, providing a foundational intelligence layer for warehouses, plants, and distribution centers. The platform utilizes AI-powered drones and computer vision to capture and analyze inventory data with 99.9% accuracy, offering insights into what exists, how it moves, and what comes next. Key features include digitized warehouse mapping, advanced search capabilities beyond barcodes, true empty location detection, 3D case counting, and occupancy level analysis. Gather AI integrates seamlessly with existing WMS and ERP systems without requiring infrastructure changes, offering flexible hardware options. It aims to improve inventory accuracy by up to 70%, reduce customer complaints by 36%, and increase operational productivity by 5x, with many customers achieving ROI in under 6 months.

MiroFlow is a high-performance, modular, and fully open-source framework designed for building intelligent AI agents. It excels in multi-step internet research and complex challenges like future event prediction, achieving top rankings on multiple benchmarks including FutureX, GAIA, HLE, xBench-DeepSearch, and BrowserComp. The framework features advanced multi-turn conversation capabilities, extensive tool ecosystem integration, and hierarchical sub-agent orchestration. Built with robust concurrency management and fault-tolerant design, MiroFlow efficiently handles rate-limited APIs and unstable networks, ensuring reliable execution of complex tasks. It is cost-effective, powered by the open-source MiroThinker model, and can run a research agent service on a single RTX 4090, relying on free, open-source tools for simple deployment and scaling.

Buffer's AI Assistant is an AI-powered tool designed to boost social media presence by generating ideas, repurposing existing posts, and summarizing long content into short, engaging social media updates. It utilizes advanced language models, specifically OpenAI's proprietary API, to create relevant and engaging content tailored to social media best practices. Users can adjust the tone, length, and structure of AI-generated posts to match their brand's voice directly within the post composer. While the AI Assistant is an optional feature, Buffer itself is a comprehensive social media management platform offering core features like posting, scheduling, planning, and analytics for various social networks, ensuring consistent publishing and sustainable growth for individuals and businesses.

Banjo Health offers an AI-powered prior authorization management solution designed by clinicians to increase efficiency and effectiveness for health plans and PBMs. The platform provides an end-to-end case management solution for prior authorizations and appeals, leveraging AI to streamline processes, reduce administrative burden, and improve decision-making speed. Key features include a Clinical Decision Tree Generator that transforms complex clinical criteria into actionable electronic decision trees, and an Appeals & Grievances Tool for efficient case management. Banjo Health is purpose-built for Payers & PBMs, integrating seamlessly with EHRs, eligibility verification tools, and claims management systems. Its no-code, user-friendly drag-and-drop interface allows for easy workflow creation and updates to clinical criteria, requiring no technical expertise.

Intuition Robotics offers ElliQ, an AI care companion robot specifically designed for older adults. ElliQ utilizes a proprietary Relationship Orchestrator that integrates with multiple LLMs to build empathetic, contextual, and ongoing relationships. This system mimics the theory of mind, leveraging context from past conversations, assessing emotional states, and employing multimodality (speech, body language, text, images, lights, sounds) for natural interactions. ElliQ's decision-making algorithm is multi-goal based, rewarding tasks related to hydration or cognitive training, and personalizes experiences over time. It proactively initiates conversations and suggestions based on user goals and availability, aiming to reduce loneliness, improve health and wellness, and enhance social connectedness.

NNPACK is an acceleration package specifically designed to optimize neural network computations on multi-core CPUs. It focuses on delivering high-performance implementations of convolutional neural network (convnet) layers. The tool is not intended for direct use by machine learning researchers but rather provides low-level performance primitives that are leveraged by leading deep learning frameworks such as PyTorch, Caffe2, MXNet, and Darknet. It supports various platforms including Linux, macOS, Android, and iOS, and offers multiple algorithms for convolutional layers, including Fourier transform, Winograd transform, and implicit matrix-matrix multiplication. Implemented in C99 and Python, NNPACK features multi-threaded SIMD-aware implementations and extensive unit test coverage.

AutoPost is an AI-powered tool designed to automate the entire website content creation and publishing process. It significantly reduces the effort and cost associated with maintaining a website by automatically writing articles using AI, optimizing them for SEO, and scheduling their publication. Users can personalize the writing style of the AI and integrate internal links for improved SEO. The tool also supports automatic sharing of articles to social media platforms. AutoPost aims to eliminate the need for a dedicated content team, allowing websites to be built once and then run autonomously with daily new content.

OAT (Online Alignment Toolkit) is a simple yet efficient open-source framework designed for running online LLM alignment algorithms. It features a distributed Actor-Learner-Oracle architecture optimized for high efficiency, utilizing vLLM for accelerated response sampling and DeepSpeed ZeRO for memory efficiency. OAT simplifies the experimental pipeline by providing an online Oracle for preference data labeling and real-time model evaluation. Researchers can simulate various feedback types, including verifiable rewards and LLM-as-a-judge, with flexible deployment options for reward models. Its modular structure facilitates rapid prototyping and experimentation, implementing cutting-edge algorithms like PPO/Dr.GRPO for online RL and Online DPO/SimPO/IPO for preference learning, fostering innovation and fair benchmarking.

vbot is an open-source solution designed for automating interactions on WeChat and enterprise WeChat platforms. It offers a comprehensive set of features including message aggregation, automated replies, and robust API integration. The tool supports various protocols, including the iPad protocol, and facilitates video downloading. Developers and businesses can leverage vbot for tasks such as group messaging, automatic responses, and custom integrations. It is built to be stable and anti-ban, supporting all programming languages, making it suitable for enterprise customization, SCRM, and SAAS applications. Additionally, vbot integrates with AI response platforms like COZE and FASTGPT for enhanced conversational capabilities.

npcpy is a comprehensive Python library designed for research and development in NLP, multimodal LLMs, Agents, ML, and Knowledge Graphs. It offers a flexible agent framework that supports both local and cloud providers, enabling users to build sophisticated AI applications. Key capabilities include multi-agent team orchestration, tool calling, and advanced functionalities like image, audio, and video generation. The library also facilitates knowledge graph integration and fine-tuning of models, making it a versatile solution for developers and researchers working with diverse AI technologies. It provides quick examples for creating personas, direct LLM calls, agent with tools, streaming, JSON output, and Pydantic structured output.

Neurite provides a unique approach to knowledge management by blending fractal geometry with mind-mapping techniques. It allows users to create and connect nodes representing text, images, videos, code, and AI agents within a virtually limitless fractal workspace. Key features include real-time fractal navigation, multi-agent AI networks for collaborative communication, and FractalGPT for structured memory mapping. The tool supports bi-directional synchronization between visual mind maps and text-based Zettelkasten archives, ensuring consistency. Neurite also integrates external knowledge sources like Wolfram Alpha and Wikipedia, and offers a Neural API for advanced users to build custom interactions within the fractal environment. A desktop version is available for Windows, Linux, and macOS, providing a full web browsing experience within link nodes.

Seahorse AI Agents is a software company dedicated to the design, development, and delivery of on-demand AI agents. The company specializes in creating custom AI agents tailored to specific tasks and business needs. By focusing on bespoke solutions, Seahorse aims to provide businesses and developers with the tools to implement advanced AI capabilities efficiently. Their expertise lies in transforming complex requirements into functional AI agents, offering a comprehensive service from initial concept to final deployment. This approach ensures that clients receive highly specialized AI solutions that integrate seamlessly into their existing operations.

obsidian-copilot is an AI assistant designed to integrate seamlessly with Obsidian, enhancing personal knowledge management. It offers a robust chat-based vault search, eliminating the need for prior indexing, and supports multimedia understanding from webpages, YouTube videos, images, PDFs, and EPUBS. Users can bring their own OpenAI-compatible or local models, ensuring data ownership and provider flexibility. Key features include a Composer for interacting with writing, Quick Commands for applying changes, and a Project Mode for creating AI-ready contexts based on folders and tags. The Plus version unlocks an autonomous Agent Mode with built-in tool calling for vault and web searches, and long-term memory capabilities.

Paperless-AI is an AI-powered extension designed for Paperless-ngx, offering advanced capabilities for automated document management. It leverages OpenAI API, Ollama, Deepseek-r1, Azure, and other compatible services to automatically analyze, classify, and tag documents. Key features include automatic detection of new documents, content analysis, and assignment of titles, tags, document types, and correspondents. The tool also provides a RAG-based AI chat for natural language document search and Q&A, understanding full document context for precise answers. Users can define rules for smart tagging and manual processing is available via a web interface for sensitive documents. It supports various AI models like Mistral, Llama, Phi-3, and Gemini, and is designed for easy installation with Docker support.

Passport Photo Maker & Editor is an online tool that simplifies the process of creating perfectly sized and compliant photos for passports, visas, ID cards, and other official documents. Users can select their country and document type, then upload a photo which is processed by AI to meet official guidelines. Key features include automatic adjustments for size and positioning, live preview, customizable background removal, and image enhancements for blurry or pixelated photos. The tool guarantees 100% compliance with international standards, offering a cost-effective and convenient alternative to traditional photo studios. It supports both printable and digital formats for online submission, ensuring privacy and security by automatically deleting processed photos from servers.

Clavel AI specializes in developing intelligent and dependable AI platforms designed to automate various tasks and significantly enhance workflow efficiency. The platform is built to support better decision-making processes within organizations, empowering teams to operate with greater speed and agility. By leveraging advanced AI models, Clavel AI helps businesses unlock new levels of creativity, efficiency, and innovation. It focuses on providing solutions that solve real-world problems, making it an invaluable asset for teams looking to streamline operations and achieve impactful results.

CallGPT 6X is a comprehensive multi-model AI workspace developed by Xerotech Ltd, offering unified access to leading AI providers such as OpenAI, Anthropic, Google, xAI, DeepSeek, Kimi, ElevenLabs, and FLUX.2 Pro. A key differentiator is its client-side privacy filtering, which detects and replaces sensitive data like NI numbers or card details before it reaches any AI server, ensuring data privacy. The platform also features a Smart Assistant Model (SAM) for automatic model routing, optimizing costs by sending queries to the most suitable provider. Users can switch models mid-conversation without losing context and edit AI-generated content directly, fostering an iterative workflow. Real-time cost tracking for every message provides full transparency on usage expenses.

Skills.sh is an open agent skills ecosystem that allows users to discover and install reusable capabilities, known as 'skills,' for their AI agents. These skills provide procedural knowledge, enabling agents to accomplish specific tasks more effectively. The platform features a leaderboard that ranks skills based on anonymous telemetry data, showcasing the most popular and useful skills in the ecosystem. Users can install skills using a simple CLI command, integrating them directly into their AI agents. The platform emphasizes security through routine audits to assess skills for malicious content, while also encouraging users to review skills before installation. Skills.sh aims to enhance AI agents by providing a wide array of specialized functionalities.